Tianshu-harness

天枢harness是一个的终端编程智能体,它要回答的核心问题是:模型何以稳定地交付, 目标不漂移、完成有证据、验证有闭环,不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境(CVM),把目标、状态、证据、资源、权限与终止条件从对话历史中外部化,由运行时持续管理。同时对deepseek v4极度优化。

Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 0f034d4379db

TypeScript, Apache-2.0 licensed. The project labels itself: agent harness, ai agent, cli, coding agent, context management, deepseek, gui and harness.

Tianshu-harness runs, with stand-ins for the services it depends on. An Argusic agent installed it in 7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The project builds from source (tsup bundle + native binary + staged runtime deps), the CLI binary launches and responds to --version, --help, sessions, and logs commands, and the test suite passes 99.9% of 19005 tests with one timing-dependent flaky failure.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.15 (measured)
recorded runs
2
last tested
stars
1,365
forks
100
open issues
45
watchers
1
size
44 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing Tianshu-harness, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • 1 test failed: scoped-git-commit 'retries through transient index.lock contention' (timing flake, passes in isolation)2 minutes
  • Node.js v18 found, requires >=240.5 minutes
Install time
7 minutes
Cold machine to finish
19 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
node dist/cli/entry.js --version returned tianshu-harness v3.25.1 (exit 0); node dist/cli/entry.js --help returned usage text (exit 0); node dist/cli/entry.js sessions returned '没有历史会话。' (exit 0); node dist/cli/entry.js logs returned 104-line log location dump (exit 0); npm run build completed all 4 stages cleanly (tsup + pack-native + stage-runtime-deps + assert-runtime-imports, exit 0); npm test ran 19005 test files, 18982 pass, 1 fail (timing flake), 22 skip
Model tokens used
116,521
Exact commit tested
0f034d4379db
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

Dist size: 149M
Node version used: v24.22.3
Now I'll compile the final result.
```json
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 7, "errors": [{"msg": "Nod…
```
tokens used
116,521
Now I'll compile the final result.
```json
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 7, "errors": [{"msg": "Nod…
```

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 7 minutes to install, slower than the median of the 83 comparable projects Argusic has measured.

Of the 84 ai-agent projects Argusic has installed and timed, Tianshu-harness was the 49th fastest to reach a running state, and 58 of 84 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.15
Argusic Runner1/3Runs with mocks92.000.11

Topics (from GitHub)

agent-harnessai-agentclicoding-agentcontext-managementdeepseekguiharnessharness-engineeringloop-engineeringpersonal-ai-assistantsuper-agenttianshutianshu-harnesstui

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/Tianshu-harness.svg)](https://argusic.com/subject/tianshu-harness)

Questions

Does Tianshu-harness run?
Tianshu-harness runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test Tianshu-harness?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0f034d4379db. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Tianshu-harness?
The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Tianshu-harness take to install?
7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does Tianshu-harness need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Tianshu-harness?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does Tianshu-harness compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, Tianshu-harness was the 49th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for Tianshu-harness?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion